In __cvdso_clock_getres_time32(), when clock_getres_fallback()
fails, it's not required to update the struct timespec res.
Bug: 159086668
Bug: 154668398
Test: run cts -m CtsBionicTestCases -t time#clock_getres_unknown
Signed-off-by: Chiawei Wang <chiaweiwang@google.com>
Change-Id: Ibb7279d4520658d5c8be76e721249d3c62267d9f
CLOCK_REALTIME in vdso data won't be updated if
__arch_use_vsyscall() returns false. It will let time()
return an incorrect time value. Since time() is designed
to return the seconds since the Epoch, using
CLOCK_REALTIME_COARSE can still fulfill the request and
never fails.
Bug: 158635600
Bug: 154668398
Bug: 157925983
Test: run bionic-benchmarks --bionic_xml vdso.xml
Test: check the time returned from time()
e.g. adb bugreport and check the date suffix
in the file name
Signed-off-by: Chiawei Wang <chiaweiwang@google.com>
Change-Id: Ibfb1b06f30f008800c0b5b61384b8fbf73b880f8
The vDSO library should only include the necessary headers required for
a userspace library (UAPI and a minimal set of kernel headers). To make
this possible it is necessary to isolate from the kernel headers the
common parts that are strictly necessary to build the library.
Refactor the unified vdso code to use the common headers.
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20200320145351.32292-26-vincenzo.frascino@arm.com
(cherry picked from commit 8c59ab839f526437831ff6d1405c9a6d93f475eb)
Signed-off-by: Mark Salyzyn <salyzyn@google.com>
Bug: 154668398
Change-Id: Ic0890fed51d4e570e50da6c553bdcbce412d0683
Signed-off-by: Chiawei Wang <chiaweiwang@google.com>
If the architecture knows at compile time that there is no VDSO capable
clocksource supported it makes sense to optimize the guts of the high
resolution parts of the VDSO out at build time. Add a helper function to
check whether the VDSO should be high resolution capable and provide a stub
which can be overridden by an architecture.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Link: https://lkml.kernel.org/r/20200207124402.530143168@linutronix.de
(cherry picked from commit 1dff4156d1f63b525c54aea7f097a657cbbbf837)
Signed-off-by: Mark Salyzyn <salyzyn@google.com>
Bug: 154668398
Change-Id: Ib024363345b8d75ffc78b3e5598a5720926f9358
Signed-off-by: Chiawei Wang <chiaweiwang@google.com>
Since all the architectures that support the generic vDSO library have
been converted to support the 32 bit fallbacks it is not required
anymore to check the return value of __cvdso_clock_get*time32_common()
before updating the old_timespec fields.
Remove the related checks from the generic vdso library.
References: c60a32ea4f45 ("lib/vdso/32: Provide legacy syscall fallbacks")
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20190830135902.20861-6-vincenzo.frascino@arm.com
(cherry picked from commit a279235ddbe975670afe2267162028ec0a312293)
Signed-off-by: Mark Salyzyn <salyzyn@google.com>
Bug: 154668398
Change-Id: I31637fcdac30262c1837b098345a2c057794ea17
Signed-off-by: Chiawei Wang <chiaweiwang@google.com>
Fix the following sparse warning in the generic vDSO library:
linux/lib/vdso/gettimeofday.c:224:5: warning: symbol
'__cvdso_clock_getres' was not declared. Should it be static?
Make it static and also mark it __maybe_unsed.
Fixes: 502a590a170b ("lib/vdso: Move fallback invocation to the callers")
Reported-by: Marc Gonzalez <marc.w.gonzalez@free.fr>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20191128111719.8282-1-vincenzo.frascino@arm.com
(cherry picked from commit ffd08731b2d632459428612431060cf902324a8d)
Signed-off-by: Mark Salyzyn <salyzyn@google.com>
Bug: 154668398
Change-Id: I9842a0811350fc325315b25ba3f41e4b626a97c0
Signed-off-by: Chiawei Wang <chiaweiwang@google.com>
A recent commit removed the NULL pointer check from the clock_getres()
implementation causing a test case to fault.
POSIX requires an explicit NULL pointer check for clock_getres() aside of
the validity check of the clock_id argument for obscure reasons.
Add it back for both 32bit and 64bit.
Note, this is only a partial revert of the offending commit which does not
bring back the broken fallback invocation in the the 32bit compat
implementations of clock_getres() and clock_gettime().
Fixes: a9446a906f52 ("lib/vdso/32: Remove inconsistent NULL pointer checks")
Reported-by: Andreas Schwab <schwab@linux-m68k.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1910211202260.1904@nanos.tec.linutronix.de
(cherry picked from commit 1638b8f096ca165965189b9626564c933c79fe63)
Signed-off-by: Mark Salyzyn <salyzyn@google.com>
Bug: 154668398
Change-Id: I3a157d989ec54577781742d69380261bc4279676
Signed-off-by: Chiawei Wang <chiaweiwang@google.com>
To address the regression which causes seccomp to deny applications the
access to clock_gettime64() and clock_getres64() syscalls because they
are not enabled in the existing filters.
That trips over the fact that 32bit VDSOs use the new clock_gettime64() and
clock_getres64() syscalls in the fallback path.
Add a conditional to invoke the 32bit legacy fallback syscalls instead of
the new 64bit variants. The conditional can go away once all architectures
are converted.
Fixes: 00b26474c2f1 ("lib/vdso: Provide generic VDSO implementation")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1907301134470.1738@nanos.tec.linutronix.de
(cherry picked from commit c60a32ea4f459f99b98d383cad3b1ac7cfb3f4be)
Signed-off-by: Mark Salyzyn <salyzyn@google.com>
Bug: 154668398
Change-Id: I8aea8f1282566f6b3f02dd021206af02469f6944
Signed-off-by: Chiawei Wang <chiaweiwang@google.com>
To allow syscall fallbacks using the legacy 32bit syscall for 32bit VDSO
builds, move the fallback invocation out into the callers.
Split the common code out of __cvdso_clock_gettime/getres() and invoke the
syscall fallback in the 64bit and 32bit variants.
Preparatory work for using legacy syscalls in 32bit VDSO. No functional
change.
Fixes: 00b26474c2f1 ("lib/vdso: Provide generic VDSO implementation")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Link: https://lkml.kernel.org/r/20190728131648.695579736@linutronix.de
(cherry picked from commit 502a590a170b3b3d0ad998ee0b639ac0b3db1dfa)
Signed-off-by: Mark Salyzyn <salyzyn@google.com>
Bug: 154668398
Change-Id: I1361d4ccfd99292c3d346325be2068b93cbcadca
Signed-off-by: Chiawei Wang <chiaweiwang@google.com>
The 32bit variants of vdso_clock_gettime()/getres() have a NULL pointer
check for the timespec pointer. That's inconsistent vs. 64bit.
But the vdso implementation will never be consistent versus the syscall
because the only case which it can handle is NULL. Any other invalid
pointer will cause a segfault. So special casing NULL is not really useful.
Remove it along with the superflouos syscall fallback invocation as that
will return -EFAULT anyway. That also gets rid of the dubious typecast
which only works because the pointer is NULL.
Fixes: 00b26474c2f1 ("lib/vdso: Provide generic VDSO implementation")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Link: https://lkml.kernel.org/r/20190728131648.587523358@linutronix.de
(cherry picked from commit a9446a906f52292c52ecbd5be78eaa4d8395756c)
Signed-off-by: Mark Salyzyn <salyzyn@google.com>
Bug: 154668398
Change-Id: I2d4563f336f8cc6b44f1b74f92467c4c6a579710
Signed-off-by: Chiawei Wang <chiaweiwang@google.com>
The x86 vdso implementation on which the generic vdso library is based on
has subtle (unfortunately undocumented) twists:
1) The code assumes that the clocksource mask is U64_MAX which means that
no bits are masked. Which is true for any valid x86 VDSO clocksource.
Stupidly it still did the mask operation for no reason and at the wrong
place right after reading the clocksource.
2) It contains a sanity check to catch the case where slightly
unsynchronized TSC values can be observed which would cause the delta
calculation to make a huge jump. It therefore checks whether the
current TSC value is larger than the value on which the current
conversion is based on. If it's not larger the base value is used to
prevent time jumps.
reason it is also completely wrong for clocksources with a smaller mask
which can legitimately wrap around during a conversion period. The core
timekeeping code does it correct by applying the mask after the delta
calculation:
(now - base) & mask
around during a conversion period because there the now > base check is
just wrong and causes stale time stamps and time going backwards issues.
Unbreak it by:
1) Removing the mask operation from the clocksource read which makes the
fallback detection work for all clocksources
2) Replacing the conditional delta calculation with a overrideable inline
function.
results in a significant performance hit for the x86 VSDO. The timekeeping
core code must have the non optimized version as it has to operate
correctly with clocksources which have smaller masks as well to handle the
case where TSC is discarded as timekeeper clocksource and replaced by HPET
or pmtimer. For the VDSO there is no replacement clocksource. If TSC is
unusable the syscall is enforced which does the right thing.
To accommodate to the needs of various architectures provide an
override-able inline function which defaults to the regular delta
calculation with masking:
(now - base) & mask
Override it for x86 with the non-masking and checking version.
This unbreaks the ARM64 syscall fallback operation, allows to use
clocksources with arbitrary width and preserves the performance
optimization for x86.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: linux-arch@vger.kernel.org
Cc: LAK <linux-arm-kernel@lists.infradead.org>
Cc: linux-mips@vger.kernel.org
Cc: linux-kselftest@vger.kernel.org
Cc: catalin.marinas@arm.com
Cc: Will Deacon <will.deacon@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: linux@armlinux.org.uk
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: paul.burton@mips.com
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: salyzyn@android.com
Cc: pcc@google.com
Cc: shuah@kernel.org
Cc: 0x7f454c46@gmail.com
Cc: linux@rasmusvillemoes.dk
Cc: huw@codeweavers.com
Cc: sthotton@marvell.com
Cc: andre.przywara@arm.com
Cc: Andy Lutomirski <luto@kernel.org>
Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1906261159230.32342@nanos.tec.linutronix.de
(cherry picked from commit 9d90b93bf325e015bbae31b83f16da5e4e17effa)
Signed-off-by: Mark Salyzyn <salyzyn@google.com>
Bug: 154668398
Change-Id: I190d30a966ab65330a230ce84f71eaa70b80792b
Signed-off-by: Chiawei Wang <chiaweiwang@google.com>
arm64 was the last architecture using CROSS_COMPILE_COMPAT_VDSO config
option. With this patch series the dependency in the architecture has
been removed.
Remove CROSS_COMPILE_COMPAT_VDSO from the Unified vDSO library code.
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
(cherry picked from commit 50a2610adec9d796b25e262734edb56ef324ce15)
Signed-off-by: Mark Salyzyn <salyzyn@google.com>
Bug: 154668398
Change-Id: I5cd788546e59e71b76af68cf845e8dd45a6bdc61
Signed-off-by: Chiawei Wang <chiaweiwang@google.com>
